From a85749dcbef8c6bad119e31f8e10d665b1788835 Mon Sep 17 00:00:00 2001 From: mefich Date: Thu, 27 Jun 2024 06:17:56 +0500 Subject: [PATCH] Update models_settings.py: add default alpha_value, add proper compress_pos_emb for newer GGUFs (#6111) --- modules/models_settings.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/modules/models_settings.py b/modules/models_settings.py index 387c5658..2e3fff9c 100644 --- a/modules/models_settings.py +++ b/modules/models_settings.py @@ -16,6 +16,7 @@ def get_fallback_settings(): 'n_ctx': 2048, 'rope_freq_base': 0, 'compress_pos_emb': 1, + 'alpha_value': 1, 'truncation_length': shared.settings['truncation_length'], 'skip_special_tokens': shared.settings['skip_special_tokens'], 'custom_stopping_strings': shared.settings['custom_stopping_strings'], @@ -58,6 +59,8 @@ def get_model_metadata(model): model_settings['rope_freq_base'] = metadata[k] elif k.endswith('rope.scale_linear'): model_settings['compress_pos_emb'] = metadata[k] + elif k.endswith('rope.scaling.factor'): + model_settings['compress_pos_emb'] = metadata[k] elif k.endswith('block_count'): model_settings['n_gpu_layers'] = metadata[k] + 1